Bayesian Investor Blog

Will young ems be created? Why and how will it happen?

Any children that exist as ems will be important as em societies mature, because they will adapt better to em environments than ems who uploaded as adults, making them more productive.

The Age of Em says little about children, presumably in part because no clear outside view predictions seem possible.

This post will use a non-Hansonian analysis style to speculate about which children will become ems. I’m writing this post to clarify my more speculative thoughts about how em worlds will work, without expecting to find much evidence to distinguish the good ideas from the bad ones.

Robin predicts few regulatory obstacles to uploading children, because he expects the world to be dominated by ems. I’m skeptical of that. Ems will be dominant in the sense of having most of the population, but that doesn’t tell us much about em influence on human society – farmers became a large fraction of the world population without meddling much in hunter-gatherer political systems. And it’s unclear whether em political systems would want to alter the relevant regulations – em societies will have much the same conflicting interest groups pushing for and against immigration that human societies have.

How much of Robin’s prediction of low regulation is due to his desire to start by analyzing a relatively simple scenario (low regulation) and add complexity later?

Emulate Human Reproduction

Emulating embryonic development isn’t obviously much harder than emulating brains [1], and should involve fairly similar techniques. So I imagine a nontrivial chance that ems will create new minds via emulated sexual reproduction.

Even if that process is slightly easier than uploading an adult mind, I’ll guess that it gets developed later, because the resulting ems take longer to become productive, which makes the return on investment lower.

Factors favoring this scenario:

• The regulatory obstacles are likely less serious than with other scenarios. I expect some concerns over the rights of emulated fetuses, but similar concerns over biological fetuses haven’t been widespread enough to be effective.
• Em’s will retain some of the human desires that cause people to have children. This approach will satisfy some of those desires.
• It should be simple to create large numbers of emulated embryos to test many hypotheses until research stumbles across a model that works.

Possible obstacles:

• The need to model in detail a wider variety of cell types (including bacteria?) than for adult brains. I’m guessing this will increase the difficulty by a factor of 2 to 5 relative to standard uploading.
• The need for greater accuracy in modeling cell growth. Small errors in modeling cell division can build up over many divisions into large errors. I’m fairly uncertain how big a problem this will be.
• The need to observe fetus development at subcellular resolutions. Would this require gathering data from within wombs? Or will fetuses be raised from conception in test tubes? The latter implies that gathering data is technically easier, but increased chances of additional ethical restrictions, as right-to-life forces will be less opposed by pro-choice lobby.
  
  Much of the necessary data can be gathered from chimpanzee embryo development, so maybe they’d only need to observe a few human fetuses. The fewer that are needed, the harder it would be for humans to unite to prevent some mothers from cooperating with such research.

I expect important effects on how fast society evolves away from current notion of human, as this scenario enables more experiments than other scenarios, involving a wide range of tweaks to human minds.

Uploaded Fetuses

The remaining scenarios will involve uploading humans after they develop a functioning brain, but before they’re adults.

I expect legal status of uploading a healthy human will default to murder (via destructive scanning) in nearly all countries. Legal system are slow to change. Relative to the rate at which em societies change, laws made by biological humans will change slowly enough that we can treat them as typically unchangeable.

Research involving aborted fetuses is much less regulated than research involving children. Brains of late-term fetuses are sufficiently developed that I expect uploading them will be about as valuable as uploading adults.

However, it’s easy to imagine that regulations concerning fetuses will change before the age of em. For example, if we can raise fetuses outside the womb, fetuses with somewhat developed brains may be treated more like people.

Cryopreserved Children

The legal restrictions could be avoided by uploading people who are legally dead. Cryopreservation or something similar is likely to be the first step in uploading, so cryopreserved people are obvious candidates for the first ems.

It seems likely that cryonics organizations will require some sort of consent from parents before they upload cryopreserved children, at least when only a few people have been uploaded.

Alcor seems to have cryopreserved exactly one person under 21. That suggests that there will be a very small number of young cryopreserved people by the age of em. Their parents’ choices could have a huge impact on which personalities are common in em society.

One reason for doubting this scenario is that cryonics organizations are conservative. Successful ones develop a focus on preservation. It’s hard to combine a preservation-oriented mindset with an attitude which promotes rapid acceptance of controversial new technologies.

Wealthy Families

Another scenario is that the first wave of uploads happens via wealthy people uploading themselves.

This approach might generate relatively little political opposition, because it’s a bit hard to worry about copies of Bill Gates or Mark Zuckerberg or Donald Trump being exploited or undercutting the average person’s wages.

It’s less clear what will happen if they want to upload their underage children. They will be able to score some political points by pointing to the desirability of keeping families together. And political concerns about protecting the children of the wealthy aren’t very strong. But people will worry about slippery slopes. I find this scenario hard to analyze.

Corporate influence on a small country

If I accept Robin’s assumption of implausibly little regulation, then I’d expect the first wave of uploads to be financed by corporations who want em workers.

That ensures high awareness of how ems will affect wages. I expect that to generate enough political hostility to ensure that most large countries stop all uploads within their jurisdictions.

So I’ll imagine that Liberia or Panama accepts gobs of corporate money to allow uploads within their jurisdiction (e.g. on cruise ships/seasteads under their flag). They avoid concerns about their citizens being “killed” (uploaded) by having regulations which ensure that it is impractical to upload a citizen of that country [2].

Such a country would be subject to conflicting pressures about any age limits on who can upload: the corporations who are financing it would want the minimum age lowered, but international political pressure would make that risky. I doubt the minimum age would go much below 16 until many people have uploaded, so this seems only slightly different from an adults-only age of em scenario.

Once one country allows uploads, that will of course create some new pressure for most countries to allow it. But the speed at which a country such as the U.S. is willing to change its laws suggests that subjective millenia will pass within em societies before most countries decide to do much. (I’m less sure about China.)

Upload near em cities

The scenario that I’m most uncertain about involves humans traveling to em city jurisdictions to upload.

Em cities will mostly be off-limits to humans, due to em environments being mostly unhealthy for humans, and maybe also due to humans causing some risks to ems. It’s unclear whether the edges of em cities will have areas where humans are welcome.

I expect em cities to quickly get full autonomy over interactions between ems within their borders, but to be slow to extend their control farther. I expect human governments to attempt to retain nearly full control over interactions involving humans, and I expect em governments to not care strongly about enabling more humans to upload.

Some em companies will have clear incentives to upload more humans, including children. Will they be able to operate freely outside of em cities? Maybe they’ll be powerful enough to override human regulations.

Uploaded Slave Children

If the relevant laws are sufficiently inflexible, maybe corporations that want ems will go places where laws are often not enforced. Somalia?

In the absence of legal systems, children aren’t obviously harder to upload than adults. Companies may be deterred from uploading relatively young children by the relatively long time it takes for them to become the most productive workers (I’m assuming companies using this approach have shorter time horizons than companies using other scenarios). But that could be offset by em-based companies with longer time horizons paying more for those workers due to their longer / better adapted careers.

Countries with weak rule of law may have crime risks that deter any organization that depends on lots of expensive equipment. But if em workers are involved, they may have abilities which make human criminals non-threatening.

This scenario would set a scary precedent, which might have important influences on future crimes within em society. It may also result in relatively disadvantaged children becoming the most successful ems. It may provide more diversity of em minds than many other scenarios.

I used the word slave in the section header because it makes the scenario more distinctive, but I expect the preference for highly competent em workers will minimize any coercion, and I don’t expect it to be much worse than marriages arranged by parents.

Conclusions

All of these scenarios include some benefits and some disturbing aspects.

Most of these scenarios seem roughly 50% likely to happen (except that the last one seems less likely).

Given all these possibilities (not mutually exclusive), I expect a fairly high probability that young ems will exist, which is bad news for those of us who want to upload as adults and earn a living.

Given how much my thinking has changed since I started to turn this into a blog post (half the post seems devoted to questions I came up with while writing), I expect I’ve overlooked some important issues. So this collection of ideas is probably still in its childhood.

Footnotes

[1] – relative to the effort an em society might devote to it; needing an extra million em-years of work would slow it down a bit, but wouldn’t prevent it.

[2] – They’d want to continue taxing the income of any of their (most productive) citizens who upload. Or more likely they’d decide they can’t count on collecting such taxes, and use a large exit tax as a substitute. That could easily persuade companies to upload only residents of other countries.